#ModGitHub stars

1. 49ruflo-agentruvnet/rufloLocal WASM and managed cloud runtimes with bounded dynamic workflows, live capability discovery and session-local mod policy.80k
2. 50ruflo-deepseek-harnessruvnet/rufloDeepSeek model harness for ruflo — agents, commands, scripts, and skills for running and evaluating DeepSeek-backed workflows within the ruflo swarm.80k
3. 51ruflo-goalsruvnet/rufloLong-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithms80k
4. 52ruflo-iot-cognitumruvnet/rufloIoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware80k
5. 53ruflo-ruosruvnet/rufloRun ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405)80k
6. 54ruflo-sparcruvnet/rufloSPARC methodology — Specification, Pseudocode, Architecture, Refinement, Completion phases with gate checks80k
7. 55ruflo-testgenruvnet/rufloTest gap detection, coverage analysis, and automated test generation — drives the testgaps background worker via hooks_worker-dispatch; SPARC Refinement-phase canonical owner80k
8. 56ruflo-workflowsruvnet/rufloPersisted workflows, native orchestration and discovery of the optional managed cloud runtime.80k
9. 57crayonjonpojonpo/cc-crayonColorful replies: themed Markdown plus inline <t color bold italic> tags the model can write, drawn with real Ink Text styling5
10. 58gemini-compactKilimcininKorOglu/claude-code-modsMoves compaction from Claude to Gemini: in summary mode Gemini summarizes the conversation and the newest messages stay verbatim, in prune mode every message stays and Gemini keeps, cuts or drops older tool calls. Off until /gemini-compact on; gemini-core holds the key, tier, model and thinking level.12
11. 59loop-breakermishgoldenberg/claude-modsNotices when Claude is going in circles (the same command failing again and again, the same code rewritten over and over) and tells Claude to step back and rethink, and tells you too.12
12. 60nudgeVedantAndhale/claude-pro-kit/nudge <goal> applies behavioral design to a product or flow: diagnose why users don't act, design interventions that remove barriers, ranked hypotheses to test, and an ethics check on every answer. Its guide reaches Claude only when you run /nudge.12
13. 61awcompactAitherium/awdkCompacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, learned from outcomes, never dropping a traceback or a summary line.11
14. 62awshAitherium/awdkawsh for Claude Code: an `aw` subagent type whose model steps are answered by a session on the local awsh harness daemon, so any harness and any backend the daemon can drive runs as a native Claude Code subagent, streamed live. Also carries the Aither World skills, the `aither` output style, MCP servers for installed bricks and portable brick hooks.11
15. 63micro-compactionruihe774/cc-micro-compactionAdds `/compact micro`: elides Read results and strips thinking, keeping the conversation structure4
16. 64desk-lookKyongSik-Yoon/cc-desktop-modClaude Code mod that redraws the terminal transcript to look like the Code tab of the Claude desktop app: prompt bubbles, markdown tables, mermaid diagrams, folded tool calls, agent cards, plan cards in the transcript, a progress band of the current step and what runs now, GitHub/GitLab PR bar, diff, activity, context, background tasks, session monitor and Markdown preview panes. The Asana and Slack panes and the plan approval card are the separate desk-asana, desk-slack and desk-plan plugins8
17. 65fast-compactNodarDavituri/fast-compact/fast-compact (and /fc): cut old tool output to its start and end in about a second, with Jev keeping whole what is still needed and every cut saved to a file. Claude Code's own /compact is untouched.8
18. 66html-shelfronanworks/claude-code-mods终端里 Claude 的回复更顺手：文件路径单击打开（HTML、文档 md/pdf/txt/json/csv/Office、图片、音视频、文件夹；脚本只在文件夹里选中不运行）；代码块画成卡片，一键复制，单条 shell 命令可 Insert 到输入框；文字里 `反引号` 写的命令也补一张卡片；悬停回复右上角 Copy all；Write/Edit 工具行带 Open；/open [N|list] 打开最近的文件（Windows / macOS / Linux）8
19. 67jev-routersatviksinha/jev-model-routerRoutes each turn to a Claude model chosen by TypeSafe's Jev, asked through the Vercel AI Gateway.7
20. 68jev-searchmukiwu/jev-search-mcpWeb search through Jev Search. Answers Claude Code's built-in WebSearch with Jev (sources and time window chosen by Jev, every result ranked by relevance) and falls back to the built-in search when Jev cannot answer. Also adds the jev_search MCP tool for explicit source or time filters, and a skill on when to use it.7
21. 69officecharlie947/mod-makerA pixel-art office in a local web page: every Claude session gets a desk, walks to the filing cabinet when it reads, types when it edits, flies paper planes when it messages, and shows a live Done-by clock7
22. 70reply-viewzhebil/claude-code-pluginsDraws Mermaid diagrams in Claude's replies as Unicode box art, makes file and folder paths open in Zed on Ctrl-click, and adds a /zed command.7
23. 71sysinit-outputroshbhatia/sysinitOne-pass local response cleanup without agent retries7
24. 72aot-evalsMahalanobis-Systems/aot-evalsPart of AOT, the Agent Optimization Toolkit, a Mahal Systems offering. Design, build, measure and iterate the evals for a production agent: a repository contract (evals/), skills that walk commands C0-C18 with exit gates, a stdlib CLI that runs the agent k times and records every attempt, and a fixed report.json schema that Claude renders into a local HTML diagnostic.6
25. 73atlasbengous/claude-code-pluginsInteractive architecture maps in the browser: zones and bricks laid out by ELK, overview arrows routed by libavoid, typed data files checked by a script, and open points discussed in threads between you and the agent; /atlas:board serves a map's page beside your session and hands what you select there to the agent; /atlas:init draws a repository's first map, each claim citing its lines6
26. 74autodev-coredjnsty23/claude-auto-devAutonomous development workflow: brainstorm, auto, audit, review, ship, plus the prd.json sprint system.6
27. 75md-renderdeepskyblue86/claude-markdown-modRedraws assistant messages as styled markdown.6
28. 76pinpointbengous/claude-code-pluginsPoint at your running app and talk to Claude: the session's address serves the app with an overlay that picks an element by a click or a zone by a drag, takes a quick label or a note, and keeps each selection in a batch you send at once; the batch reaches the session as a prompt, each element described by its selector, role, accessible name, box and styles, each zone with an image of it6
29. 77typesafe-modBeLazy167/typesafe-modRoutes decisions to TypeSafe's Jev model: ranks installed skills for each prompt, and answers the agent's own this-or-that questions when confident.6
30. 78dispatch-gatewdsewdser-bit/claude-code-modsA soft gate on the main session: reminds it, then refuses once per stretch, to hand work to a subagent; and refuses one Claude subagent per hour past three.5
31. 79korean-uiKimSuro5773/korean-uiClaude Code의 명령어 설명과 /config 설정 항목을 한국어로 표시합니다. 번역되지 않은 문구는 /korean-ui-translate로 Haiku가 번역해서 저장합니다. 요청을 함께 쓰면 번역을 고칠 수 있습니다.5
32. 80plugin-healthray-manaloto/dotfilesReports at session start when plugins declared in settings are not actually installed or are disabled for this project5
33. 81ptc-runwdsewdser-bit/claude-code-modsProgrammatic tool calling: run_code runs a JS program that calls read/glob/grep/edit/bash in a sandbox and returns only the final value; large results spill to refs.5
34. 82claude-image-generationhex/claude-image-generationGenerate and edit images using Google Gemini, OpenAI GPT Image, xAI Grok Image, and OpenRouter APIs15
35. 83autopilot-progressIT-Shelter-Labs/Claude-ModsA Claude Code mod from IT-Shelter-Labs/Claude-Mods.14
36. 84ctxIT-Shelter-Labs/Claude-ModsA Claude Code mod from IT-Shelter-Labs/Claude-Mods.14
37. 85decision-ledgerYeonwooSung/my-claude-code-modsDecision Ledger1.1k
38. 86akaakasecurity/ai-tcAI Traffic Control — inspect and govern AI prompts in Claude Code. Detection runs locally; events are recorded to a local SQLite store on your machine.13
39. 87agent-bridgerennerdo30/agent-bridgeTalk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask).3
40. 88agent-mobile-observerCoolkidlab-Yin/agent-mobile-control手機聊天室的觀測 mod：回合開始/結束與手機直送抵達，POST 給 :8899/api/observe；純觀測不改行為3
41. 89agent-mobile-permCoolkidlab-Yin/agent-mobile-control手機聊天室的授權卡 mod：桌面對話的 Bash 授權與選擇題同時送到手機，誰先按算誰；取代 settings.json 的 perm-bridge.js（mod 出錯時引擎自動退回它）3
42. 90catalyst-probesTransmuteLabs/CatalystConsultation and prompt engine for Claude Mods. The module is the core; [probe.<id>] tables in probes.toml are the consultants and [prompt.<id>] tables author a system-prompt section, a tool description or a command description. The only carrier is the mod: a CLAUDE_*_CARRIER handle set to mod or left empty/unset arms the probe here; any other value loudly refuses the calls this probe acts on (the patch-side copy is gone).3
43. 91claudiverse-seatPromises/claudiverse-ossMakes every Claude Code session (2.1.287+) a claudiverse seat: registration, remote input and interrupt, the message mirror, remote answers. Works offline as plain Claude Code.3
44. 92cockpit-sharedmartineserios/thebranaSource of truth for the code every brana cockpit mod carries (allowlist, run, state, probe, snapshot). Never installed: the engine refuses imports outside a plugin's folder, so system/scripts/mods-sync-shared.sh vendors these files into each mod's hooks/_shared/ and validate Check 77a asserts the copies are byte-identical.3
45. 93codemodeejklock/claude-code-modeOne codemode tool: the model writes a script that calls the session's tools, and only the script's output returns.3
46. 94en-cristianoGrandullon/diariovida-modsDebajo de cada acción de Claude, una línea en español normal que explica qué está haciendo (leer, crear, mover, borrar, buscar...). Para entender a Claude sin saber informática.3
47. 95hangulproagent-ai/claude-hangulOS 한글 입력기 없이 Claude Code 프롬프트에서 두벌식·세벌식 390·세벌식 최종으로 한글을 친다3
48. 96prompt-spellcheckljmerza/prompt-spellcheckFixes spelling and typos in each typed prompt with a fast model before the main model reads it3